onboarding-cro
Pass
Audited by Gen Agent Trust Hub on Feb 27, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of markdown documentation and instructions for the AI agent to act as a Conversion Rate Optimization (CRO) expert. No executable scripts or system commands were found.
- [INDIRECT_PROMPT_INJECTION]: The skill instructions include a check for a local file named
.claude/product-marketing-context.mdto gather context. While this represents a data ingestion surface, it is a standard practice for providing localized context to the agent and does not involve automated execution of external data. - Ingestion points: Reads
.claude/product-marketing-context.mdin SKILL.md. - Boundary markers: None explicitly defined in the prompt interpolation.
- Capability inventory: No subprocesses, network operations, or file-writing capabilities detected.
- Sanitization: Not applicable as no code is executed.
Audit Metadata